English
Related papers

Related papers: Learning-Rate-Free Learning by D-Adaptation

200 papers

With the emergence of distributed data, training machine learning models in the serverless manner has attracted increasing attention in recent years. Numerous training approaches have been proposed in this regime, such as decentralized SGD.…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-08-25 Hongchang Gao , Heng Huang

When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-tuning learning rates is resource intensive, while fixed…

Machine Learning · Computer Science 2020-07-13 Tyler B. Johnson , Pulkit Agrawal , Haijie Gu , Carlos Guestrin

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

Backtracking linesearch is the de facto approach for minimizing continuously differentiable functions with locally Lipschitz gradient. In recent years, it has been shown that in the convex setting it is possible to avoid linesearch…

Optimization and Control · Mathematics 2024-03-14 Puya Latafat , Andreas Themelis , Lorenzo Stella , Panagiotis Patrinos

We consider linear prediction with a convex Lipschitz loss, or more generally, stochastic convex optimization problems of generalized linear form, i.e.~where each instantaneous loss is a scalar convex function of a linear function. We show…

Machine Learning · Computer Science 2022-11-01 Idan Amir , Roi Livni , Nathan Srebro

Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to flatten the landscape of deep learning models. Integrating…

Machine Learning · Computer Science 2023-03-02 Hao Sun , Li Shen , Qihuang Zhong , Liang Ding , Shixiang Chen , Jingwei Sun , Jing Li , Guangzhong Sun , Dacheng Tao

We propose a new first-order method for minimizing nonconvex functions with a Lipschitz continuous gradient and Hessian. The proposed method is an accelerated gradient descent with two restart mechanisms and finds a solution where the…

Optimization and Control · Mathematics 2024-06-19 Naoki Marumo , Akiko Takeda

Like many optimization algorithms, Stochastic Variational Inference (SVI) is sensitive to the choice of the learning rate. If the learning rate is too small, the optimization process may be slow, and the algorithm might get stuck in local…

Computational Engineering, Finance, and Science · Computer Science 2024-12-23 Maximilian Dinkel , Gil Robalo Rei , Wolfgang A. Wall

We study how the learning rate affects the performance of a relaxed randomized Kaczmarz algorithm for solving $A x \approx b + \varepsilon$, where $A x =b$ is a consistent linear system and $\varepsilon$ has independent mean zero random…

Numerical Analysis · Mathematics 2022-08-10 Nicholas F. Marshall , Oscar Mickelin

Deep learning algorithms are often said to be data hungry. The performance of such algorithms generally improve as more and more annotated data is fed into the model. While collecting unlabelled data is easier (as they can be scraped easily…

Machine Learning · Computer Science 2024-01-04 Abhishek Sinha , Shreya Singh

We study distributed optimization algorithms for minimizing the average of \emph{heterogeneous} functions distributed across several machines with a focus on communication efficiency. In such settings, naively using the classical stochastic…

Machine Learning · Computer Science 2020-11-18 Ilqar Ramazanli , Han Nguyen , Hai Pham , Sashank J. Reddi , Barnabas Poczos

Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we…

Machine Learning · Computer Science 2019-02-26 Guoqiang Zhang , Kenta Niwa , W. Bastiaan Kleijn

We propose a new family of adaptive first-order methods for a class of convex minimization problems that may fail to be Lipschitz continuous or smooth in the standard sense. Specifically, motivated by a recent flurry of activity on…

Optimization and Control · Mathematics 2021-07-19 Kimon Antonakopoulos , Panayotis Mertikopoulos

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a…

Machine Learning · Computer Science 2019-11-26 Bartosz Wójcik , Łukasz Maziarka , Jacek Tabor

The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the properties of the loss function. The most decisive among these…

Machine Learning · Computer Science 2025-10-31 Tomas Hrycej , Bernhard Bermeitinger , Massimo Pavone , Götz-Henrik Wiegand , Siegfried Handschuh

In stochastic convex optimization problems, most existing adaptive methods rely on prior knowledge about the diameter bound $D$ when the smoothness or the Lipschitz constant is unknown. This often significantly affects performance as only a…

Optimization and Control · Mathematics 2025-10-08 Clément Lezane , Alexandre d'Aspremont

This paper develops a policy learning method for tuning a pre-trained policy to adapt to additional tasks without altering the original task. A method named Adaptive Policy Gradient (APG) is proposed in this paper, which combines Bellman's…

Machine Learning · Computer Science 2025-09-29 Wenjian Hao , Zehui Lu , Zihao Liang , Tianyu Zhou , Shaoshuai Mou

Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in face of noisy objectives. However, Adam can have undesirable…

Machine Learning · Computer Science 2021-07-06 Chen Zhu , Yu Cheng , Zhe Gan , Furong Huang , Jingjing Liu , Tom Goldstein

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set G up to the smallest possible additive term, called the convergence rate. When the reference set…

Statistics Theory · Mathematics 2008-03-04 Jean-Yves Audibert

Adaptive gradient optimizers (AdaGrad), which dynamically adjust the learning rate based on iterative gradients, have emerged as powerful tools in deep learning. These adaptive methods have significantly succeeded in various deep learning…

Optimization and Control · Mathematics 2024-12-31 Ruinan Jin , Xiaoyu Wang , Baoxiang Wang